I've also seen this checking randomForest. It looks like the result of
memory corruption, so please try with valgrind and/or using gctorture.
On Wed, 29 Nov 2006, Liaw, Andy wrote:
> Dear R-devel,
>
> Kurt had alerted me to the problem that the randomForest package that I
> maintain has been failing checks in R-devel. However, I just can't see
> why or where it's failing. I'd very much appreciate any pointer.
>
> The failure occur when running the example code in varImpPlot.Rd:
>
>> varImpPlot(mtcars.rf)
> Error in par(opar) : invalid value specified for graphical parameter
> "xaxp"
> Execution halted
>
> However, I do not have "par(opar)" or set xaxp anywhere in any of
the
example has par(opar) in it (although not I think in the case you are
using), as do several graphics functions.
> .Rd or .R files in the package. In varImpPlot(), I used the construct:
>
> if (nmeas > 1) {
> op <- par(mfrow=c(1, 2), mar=c(4, 5, 4, 1), mgp=c(2, .8, 0),
> oma=c(0, 0, 2, 0))
> on.exit(par(op))
> }
>
> The weird thing is that even after I commented out the entire section
> above, I still get the same error at the same place! Running the
> original code in an interactive session produced no error or warning.
> I'm quite at my wit's end. Would very much appreciate any help!
>
> Best,
> Andy
>
>
>
> Andy Liaw, PhD
> Biometrics Research PO Box 2000 RY33-300
> Merck Research Labs Rahway, NJ 07065
> andy_liaw(a)merck.com 732-594-0820
>
>
>
>
------------------------------------------------------------------------------
> Notice: This e-mail message, together with any attachments,...{{dropped}}
>
> ______________________________________________
> R-devel at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
>
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595